© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146210
    Prev
    Next
    INDEX
    Explanations

    detail

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’
    2.13
    in
    1.77
     is
    1.55
    ר
    1.47
    er
    1.38
    '
    1.38
    2
    1.34
    ه
    1.33
    ید
    1.25
    an
    1.24
    POSITIVE LOGITS
    이지만
    1.34
    的设计
    1.25
    ために
    1.24
    大脑
    1.23
    的产品
    1.22
    大战
    1.21
    大量
    1.20
     anciennes
    1.18
    ფორმა
    1.18
     effectuer
    1.17
    Activations Density 0.001%

    No Known Activations